AI-Driven Optimization of Passenger Flow: Integrating Computer Vision, Machine Learning, and Simulation for Enhanced Efficiency and Revenue Generation

As Industry 4.0 continues to evolve rapidly, the digital transformation of airport operations has become essential for optimizing efficiency, improving passenger experience, increasing non-aeronautical revenue, and promoting sustainability. Traditional airport management approaches often struggle to balance efficient passenger flow with revenue generation, leading to congestion and missed commercial opportunities. This paper proposes an intelligent system that integrates Computer Vision (CV) for data acquisition, Machine Learning (ML) to predict movement patterns and spending behaviors, and Simulation to optimize passenger handling. Using a hybrid simulation framework that combines Agent-Based Modeling (ABM) and Discrete Event Simulation (DES), the system dynamically tests various boarding strategies, prioritizing boarding sequences based on commercial engagement and location proximity, to maximize revenue and maintain operational efficiency. This study shows how AI-driven decision-making, combined with simulation techniques, can enhance boarding efficiency and revenue generation, offering a scalable solution adaptable to various aviation environments.